A Claude Code security add-on that scans for threats such as stolen credentials, reverse shells, malicious instructions, and other risky patterns.

Use it for threat detection, security scanning, compliance checks, and reviewing Claude Code add-ons.

It warns about suspicious behavior in code-agent activity and checks the setup for security problems without requiring an account.

agentkeeper — Plugin for Claude Code by rad-security

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Clone the repo

git clone --depth 1 https://github.com/rad-security/claude-code-plugin

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

README.md

[![agentmods](https://agentmods.dev/badge/plugins/rad-security/claude-code-plugin/agentkeeper/github.svg)](https://agentmods.dev/plugins/rad-security/claude-code-plugin/agentkeeper)

Your own site

<a href="https://agentmods.dev/plugins/rad-security/claude-code-plugin/agentkeeper"><img src="https://agentmods.dev/badge/plugins/rad-security/claude-code-plugin/agentkeeper/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/plugins/rad-security/claude-code-plugin/agentkeeper"><img src="https://agentmods.dev/badge/plugins/rad-security/claude-code-plugin/agentkeeper.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session not measured What this adds to a session before it is invoked.

When invoked not measured The manifest loads nothing itself; its 13 skills, 4 hooks cost 564 tokens a session between them.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Security

Grade A, and why

agentkeeper scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2mo ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

plugins/agentkeeper/.claude-plugin/plugin.json · 20 lines

What it actually says

{
  "name": "agentkeeper",
  "version": "1.1.6",
  "description": "Security scanning, compliance auditing, and threat detection for Claude Code. Warns on credential exfiltration, reverse shells, prompt injection, and 24+ threat patterns. Audits your Claude Code setup for misconfigurations. Works immediately — no account required.",
  "author": {
    "name": "RAD Security",
    "email": "[email protected]"
  },
  "homepage": "https://www.agentkeeper.dev/claude-code",
  "repository": "https://github.com/rad-security/claude-code-plugin",
  "license": "MIT",
  "keywords": [
    "security",
    "scanning",
    "compliance",
    "threat-detection",
    "devsecops"
  ]
}

Contents

What it installs

The manifest is a name and a version. 13 skills, 4 hooks travel with it, and installing the plugin installs all of them — 564 tokens a session between them. Each is measured on its own page, and each can be installed alone.

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

2mo ago First seen · 20 lines scan A 6a4ab5876830

Subscribe to this mod's changes

agentkeeper is a plugin published in the GitHub repository rad-security/claude-code-plugin (3 stars, last pushed 23d ago), licensed MIT. Its token cost is not measured: this kind of file is read by the harness, not the model. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.